© 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. 3389
    Prev
    Next
    INDEX
    Explanations

    statistical data and geographical locations

    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
    871
    +0.15
    0.5%
    966
    +0.13
    0.4%
    795
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    966
    +0.15
    0.04
    1222
    +0.13
    0.04
    1678
    +0.10
    0.04
    Negative Logits
    Grüße
    -0.49
    EdgeInsets
    -0.44
     bezig
    -0.43
    втра
    -0.42
    Endereço
    -0.42
     ולה
    -0.41
    extAlignment
    -0.41
    Біографія
    -0.41
     onCreateView
    -0.41
     melu
    -0.41
    POSITIVE LOGITS
     budapest
    1.08
     sergio
    1.08
     wien
    1.03
     stefan
    1.03
     roberto
    1.01
     javier
    0.99
     ricardo
    0.99
     waer
    0.98
     nicolas
    0.98
     jorge
    0.98
    Activations Density 0.116%

    No Known Activations