© 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. 14396
    Prev
    Next
    INDEX
    Explanations

    numbers in a specific format

    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
    687
    +0.17
    0.7%
    1978
    +0.15
    0.6%
    31
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    687
    +0.17
    0.06
    31
    +0.15
    0.05
    1306
    +0.14
    0.06
    Negative Logits
    Hvad
    -0.76
    Noter
    -0.70
    Prí
    -0.69
    Fø
    -0.68
    Kilder
    -0.67
    Referencer
    -0.66
    Hvem
    -0.65
    Nuorodos
    -0.65
    ഊ
    -0.64
    astéro
    -0.63
    POSITIVE LOGITS
     meis
    0.96
     peugeot
    0.96
     bayern
    0.93
    8
    0.92
     maroc
    0.92
     milano
    0.89
     nomine
    0.88
     italia
    0.85
     frankfurt
    0.84
     EIGHT
    0.84
    Activations Density 0.144%

    No Known Activations