© 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. 3762
    Prev
    Next
    INDEX
    Explanations

    legal and regulatory language related to education and governance

    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
    1741
    +0.18
    0.6%
    1757
    +0.12
    0.4%
    382
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1265
    +0.18
    0.06
    76
    +0.12
    0.06
    394
    +0.12
    0.06
    Negative Logits
     vne
    -0.77
     istan
    -0.67
    autogui
    -0.67
     habet
    -0.66
     hoga
    -0.66
     santiago
    -0.65
     potest
    -0.65
     sevilla
    -0.65
     haer
    -0.64
     palab
    -0.64
    POSITIVE LOGITS
     however
    0.58
     albeit
    0.48
     namely
    0.47
     including
    0.46
     but
    0.45
    Panamoan
    0.43
    however
    0.42
     tartalomajánló
    0.42
    chule
    0.41
     whether
    0.41
    Activations Density 0.361%

    No Known Activations