© 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. 3396
    Prev
    Next
    INDEX
    Explanations

    information related to diseases, specifically focusing on the spread, prevention, and effects of transmitted diseases and conditions

    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
    227
    +0.12
    0.4%
    297
    +0.11
    0.3%
    394
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2036
    +0.12
    0.05
    227
    +0.11
    0.07
    1819
    +0.10
    0.07
    Negative Logits
     sappi
    -1.20
     parteci
    -1.13
     vogli
    -1.11
     scopri
    -1.06
     voleva
    -0.97
     rispond
    -0.96
     abbra
    -0.93
     rimanere
    -0.91
     espri
    -0.91
     credere
    -0.91
    POSITIVE LOGITS
     such
    0.81
     including
    0.78
     like
    0.65
     Including
    0.65
    such
    0.64
    including
    0.60
     takich
    0.57
     substances
    0.55
     namely
    0.55
     categories
    0.55
    Activations Density 0.531%

    No Known Activations