© 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. 4409
    Prev
    Next
    INDEX
    Explanations

    phrases related to conveying information or instructions

    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
    1056
    +0.12
    0.4%
    314
    +0.12
    0.3%
    1264
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1056
    +0.12
    0.06
    11
    +0.12
    0.04
    2000
    +0.09
    0.04
    Negative Logits
     kram
    -0.65
     lele
    -0.64
     restera
    -0.60
     poil
    -0.60
     pama
    -0.60
     palab
    -0.58
     kuku
    -0.58
     Nguy
    -0.57
     paus
    -0.57
     thuy
    -0.57
    POSITIVE LOGITS
     by
    0.57
    jątk
    0.54
     oleh
    0.51
     asked
    0.47
     instructed
    0.47
     told
    0.47
     to
    0.46
     piecewise
    0.45
     coerci
    0.45
    Told
    0.45
    Activations Density 0.230%

    No Known Activations