© 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. 14512
    Prev
    Next
    INDEX
    Explanations

    mentions of personal names and social media handles

    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
    1343
    +0.23
    0.7%
    227
    +0.17
    0.5%
    1978
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.23
    0.04
    227
    +0.17
    0.03
    1343
    +0.14
    0.03
    Negative Logits
     fta
    -1.48
     aen
    -1.46
     ftu
    -1.43
     chery
    -1.42
     stockholm
    -1.42
     budapest
    -1.41
     lyon
    -1.39
     desir
    -1.39
     wien
    -1.38
     milf
    -1.36
    POSITIVE LOGITS
    ostante
    0.56
    Màu
    0.55
     viewDid
    0.54
    ocry
    0.53
    abspath
    0.53
     ahol
    0.53
     arcilla
    0.53
     tami
    0.52
    tonsoft
    0.52
    ocyan
    0.51
    Activations Density 0.079%

    No Known Activations