© 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. 3791
    Prev
    Next
    INDEX
    Explanations

    keywords related to specific technical terms or information, such as 'nook', 'interest', 'depreciation', and 'make'

    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
    1870
    +0.17
    0.5%
    1510
    +0.14
    0.4%
    468
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.17
    0.04
    1510
    +0.14
    0.05
    468
    +0.12
    0.05
    Negative Logits
     scopri
    -1.17
     voleva
    -1.16
     dimenti
    -1.11
     faceva
    -1.10
     dovre
    -1.07
     vogliamo
    -1.06
     succede
    -1.04
     vuol
    -1.04
     facciamo
    -1.02
     doveva
    -1.02
    POSITIVE LOGITS
     and
    1.23
     &
    1.13
     \&
    1.01
     и
    0.97
     và
    0.91
     $\&$
    0.91
    และ
    0.91
    和
    0.88
    &
    0.86
    \&
    0.84
    Activations Density 0.841%

    No Known Activations