© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 14190
    Prev
    Next
    INDEX
    Explanations

    phrases indicating potential challenges or drawbacks

    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
    1387
    +0.11
    0.3%
    1974
    +0.09
    0.3%
    1793
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1387
    +0.11
    0.05
    1948
    +0.09
    0.05
    963
    +0.08
    0.04
    Negative Logits
     Sén
    -0.65
     predecess
    -0.64
     ossia
    -0.59
     saluti
    -0.57
     thuy
    -0.56
     hcm
    -0.56
     ladri
    -0.56
     perciò
    -0.56
    Formazione
    -0.55
     poulet
    -0.55
    POSITIVE LOGITS
     skimage
    0.68
     pymongo
    0.66
     pouvaient
    0.61
     contribué
    0.55
     pylab
    0.54
     sometimes
    0.51
    Takk
    0.50
     tempfile
    0.50
     pymysql
    0.49
     Może
    0.49
    Activations Density 0.424%

    No Known Activations