Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 1531
    Prev
    Next
    INDEX
    Explanations

    descriptions of features and functionalities related to digital tools or technologies

    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
    478
    +0.14
    0.5%
    966
    +0.12
    0.4%
    1870
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2030
    +0.14
    0.02
    188
    +0.12
    0.02
    966
    +0.11
    0.02
    Negative Logits
     indestru
    -1.10
     philanth
    -0.90
     intersper
    -0.84
     disgra
    -0.81
     maneu
    -0.80
     indoc
    -0.80
     encomp
    -0.79
     inconce
    -0.79
     disagre
    -0.79
     emphat
    -0.78
    POSITIVE LOGITS
     capabilities
    1.10
     abilities
    1.03
     capability
    0.97
    ABILITIES
    0.87
     Capabilities
    0.80
    capabilities
    0.80
     Abilities
    0.80
    abilities
    0.77
    Capabilities
    0.77
     ability
    0.77
    Activations Density 0.114%

    No Known Activations