© 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. 3575
    Prev
    Next
    INDEX
    Explanations

    references to legal documents or requests for information

    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
    1870
    +0.12
    0.4%
    1150
    +0.12
    0.4%
    946
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.12
    0.07
    919
    +0.12
    0.03
    1105
    +0.09
    0.05
    Negative Logits
     Mlle
    -1.59
     effe
    -1.52
     unden
    -1.44
     scrat
    -1.43
     lidl
    -1.42
     oleo
    -1.41
     affor
    -1.40
     peppa
    -1.40
     lyon
    -1.39
     squa
    -1.39
    POSITIVE LOGITS
    <bos>
    0.68
     laws
    0.66
     regulations
    0.66
     certification
    0.65
     hearings
    0.63
     efforts
    0.63
     legislation
    0.62
     mechanism
    0.62
     allegations
    0.61
     protections
    0.61
    Activations Density 0.405%

    No Known Activations