© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 14147
    Prev
    Next
    INDEX
    Explanations

    terms related to character development and transformation

    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
    1842
    +0.15
    0.5%
    736
    +0.13
    0.4%
    511
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.15
    0.07
    509
    +0.13
    0.07
    163
    +0.13
    0.02
    Negative Logits
     levis
    -1.35
     antik
    -1.30
     silikon
    -1.29
     makro
    -1.26
     mef
    -1.26
     keramik
    -1.23
     dises
    -1.22
     saar
    -1.21
     lele
    -1.21
     aen
    -1.20
    POSITIVE LOGITS
    Jakie
    0.67
     himself
    0.66
    Dlaczego
    0.66
    Czym
    0.65
    Și
    0.64
    Bardzo
    0.64
    Zurück
    0.64
    Genau
    0.63
    Jeder
    0.63
    Dzięki
    0.62
    Activations Density 0.595%

    No Known Activations