© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11524
    Prev
    Next
    INDEX
    Explanations

    information related to products, reports, events, and content updates

    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
    764
    +0.18
    0.6%
    227
    +0.17
    0.6%
    845
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.18
    0.07
    227
    +0.17
    0.08
    845
    +0.13
    0.04
    Negative Logits
     PLWABN
    -0.62
     heapq
    -0.59
    ഉ
    -0.58
    AndEndTag
    -0.56
    ftagPool
    -0.56
    月中旬
    -0.56
    كويكب
    -0.56
    futbolista
    -0.55
    astéro
    -0.55
    Při
    -0.55
    POSITIVE LOGITS
     shenan
    1.14
     snoopy
    1.06
     intersper
    1.04
     maneu
    0.98
     resear
    0.96
     accla
    0.96
     attemp
    0.96
     encomp
    0.96
     scrat
    0.96
     pooh
    0.93
    Activations Density 0.906%

    No Known Activations