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

    Neuronpedia

    Jacobian LensNEW
    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. 6124
    Prev
    Next
    INDEX
    Explanations

    words related to instructions and implementations

    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
    1150
    +0.11
    0.3%
    856
    +0.10
    0.3%
    1343
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    249
    +0.11
    0.06
    490
    +0.10
    0.03
    955
    +0.09
    0.06
    Negative Logits
     héri
    -0.68
    amsmath
    -0.59
     Marín
    -0.58
    JsonHelper
    -0.57
    amssymb
    -0.57
    lipas
    -0.56
     prét
    -0.56
    Atsauces
    -0.56
     négoci
    -0.55
    mavi
    -0.53
    POSITIVE LOGITS
    ⓧ
    0.78
     whichever
    0.76
    /**
    0.72
     whatsoever
    0.64
     alike
    0.63
    <?
    0.61
    etc
    0.60
     depending
    0.59
     whatever
    0.58
    URBANA
    0.58
    Activations Density 0.506%

    No Known Activations