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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3309
    Prev
    Next
    INDEX
    Explanations

    mentions of political activities or agreements involving specific countries and historical events

    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
    511
    +0.10
    0.3%
    1842
    +0.09
    0.3%
    946
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    880
    +0.10
    0.04
    864
    +0.09
    0.04
    946
    +0.09
    0.04
    Negative Logits
     scrat
    -1.23
     edp
    -1.20
     increa
    -1.20
     suscep
    -1.19
     effe
    -1.19
     swarovski
    -1.17
     thut
    -1.17
     affor
    -1.16
     eyel
    -1.16
     disreg
    -1.16
    POSITIVE LOGITS
     released
    0.80
     kidnapped
    0.71
     detained
    0.70
     captivity
    0.69
     prisoners
    0.69
     imprisoned
    0.68
     prisoner
    0.67
    Carreira
    0.66
     hostages
    0.65
     release
    0.64
    Activations Density 0.370%

    No Known Activations