© 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. 13851
    Prev
    Next
    INDEX
    Explanations

    informational snippets including personal introductions and details about projects or achievements

    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
    198
    +0.14
    0.4%
    752
    +0.11
    0.3%
    227
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.14
    0.07
    1533
    +0.11
    0.02
    752
    +0.10
    0.04
    Negative Logits
    <bos>
    -0.66
    ];//
    -0.65
     decorativas
    -0.64
     prochaines
    -0.62
    ">/
    -0.61
     nouveautés
    -0.61
    InjectMocks
    -0.60
    Initializable
    -0.60
     modalités
    -0.59
     peines
    -0.59
    POSITIVE LOGITS
     venezuela
    0.73
     hcm
    0.69
     Sinal
    0.69
     endom
    0.68
     guatemala
    0.67
     colombia
    0.67
     santiago
    0.66
     palab
    0.65
     seoul
    0.64
     Compañ
    0.63
    Activations Density 0.559%

    No Known Activations