© 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. 12971
    Prev
    Next
    INDEX
    Explanations

    numeric values and technical terms in a structured document such as assignments, dates, and flags

    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
    990
    +0.11
    0.3%
    227
    +0.10
    0.3%
    1505
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.11
    0.08
    990
    +0.10
    0.05
    783
    +0.10
    0.04
    Negative Logits
    Serviço
    -1.19
    SOBRE
    -1.04
    Apesar
    -1.04
    Composição
    -1.03
    Nós
    -1.03
    Saiba
    -1.02
    Ανα
    -1.02
    Característica
    -1.01
    Público
    -1.01
    Conheça
    -1.00
    POSITIVE LOGITS
     snoopy
    2.44
     reluct
    2.43
     increa
    2.43
     maneu
    2.41
     strick
    2.41
     purcha
    2.40
     impra
    2.38
     emphat
    2.38
     guarante
    2.37
     desir
    2.36
    Activations Density 0.570%

    No Known Activations