© 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. 14426
    Prev
    Next
    INDEX
    Explanations

    dollar amounts or numerical values

    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
    1978
    +0.17
    0.7%
    776
    +0.15
    0.6%
    196
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    196
    +0.17
    0.06
    776
    +0.15
    0.07
    313
    +0.14
    0.05
    Negative Logits
    astéro
    -0.76
    ഊ
    -0.71
    Izvori
    -0.71
    spesies
    -0.66
    loài
    -0.65
    Nuorodos
    -0.65
    <bos>
    -0.64
    Setiap
    -0.63
    Біографія
    -0.63
    Viited
    -0.62
    POSITIVE LOGITS
     deleter
    0.97
     milano
    0.95
    7
    0.94
     napoli
    0.89
     peccato
    0.89
     bandung
    0.88
     ritard
    0.86
     italia
    0.85
     SEVENTH
    0.84
     ❓
    0.84
    Activations Density 0.175%

    No Known Activations