© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 12809
    Prev
    Next
    INDEX
    Explanations

    mentions of political situations and disputes, specifically focused on Israel

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1120
    +0.16
    0.5%
    1842
    +0.16
    0.5%
    939
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    939
    +0.16
    0.07
    880
    +0.16
    0.04
    1655
    +0.10
    0.04
    Negative Logits
     funko
    -0.93
    <bos>
    -0.86
     disreg
    -0.85
     logitech
    -0.84
     cytoplas
    -0.80
     hasbro
    -0.80
     ryzen
    -0.79
     hentai
    -0.77
     paillettes
    -0.76
     stickied
    -0.76
    POSITIVE LOGITS
    GraphicsUnit
    0.53
     jugu
    0.49
     souverain
    0.47
    InjectAttribute
    0.45
    ISupport
    0.43
    mientos
    0.43
    MigrationBuilder
    0.43
     occupied
    0.43
     settlements
    0.43
     Palestinians
    0.42
    Activations Density 0.483%

    No Known Activations