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. 15471
    Prev
    Next
    INDEX
    Explanations

    information related to historical practices or events

    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
    198
    +0.17
    0.5%
    872
    +0.15
    0.4%
    1056
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.17
    0.06
    371
    +0.15
    0.03
    872
    +0.07
    0.06
    Negative Logits
    DockStyle
    -0.59
    aarrggbb
    -0.58
    setViewportView
    -0.57
    getKeyCode
    -0.57
    AutoScaleMode
    -0.55
    AntiForgeryToken
    -0.54
    HostException
    -0.54
    AnchorStyles
    -0.54
     للمعارف
    -0.53
    moveToNext
    -0.53
    POSITIVE LOGITS
     unwarran
    1.22
     ftu
    1.16
     Juf
    1.13
     disagre
    1.12
     reluct
    1.11
     aen
    1.09
     seiz
    1.09
     perfon
    1.07
     fup
    1.06
     poff
    1.06
    Activations Density 0.523%

    No Known Activations